Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Models

arXiv:2404.00506v1 Announce Type: new
Abstract: Machine unlearning aims to remove information derived from forgotten data while preserving that of the remaining dataset in a well-trained model. With the increasing emphasis on data privacy, several approaches to machine unlearning have emerged. However, these methods typically rely on complete supervision throughout the unlearning process. Unfortunately, obtaining such supervision, whether for the forgetting or remaining data, can be impractical due to the substantial cost associated with annotating real-world datasets. This challenge prompts us …

abstract arxiv cs.lg data data privacy dataset free however information machine privacy process supervision type unlearning